ShadowCoT introduces a reasoning-level backdoor attack on LLMs achieving 94.4% attack success rate and 88.4% hijacking success rate with 0.15% parameter updates via internal state conditioning and reasoning chain pollution.
BoT: Breaking Long Thought Processes of o1-like Large Language Models through Backdoor Attack
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Reinforcement learning is advanced for communication-efficient federated optimization and for preference-aligned, contextually safe policies in large language models.
citing papers explorer
-
ShadowCoT: Cognitive Hijacking for Stealthy Reasoning Backdoors in LLMs
ShadowCoT introduces a reasoning-level backdoor attack on LLMs achieving 94.4% attack success rate and 88.4% hijacking success rate with 0.15% parameter updates via internal state conditioning and reasoning chain pollution.
-
Reinforcement Learning for Scalable and Trustworthy Intelligent Systems
Reinforcement learning is advanced for communication-efficient federated optimization and for preference-aligned, contextually safe policies in large language models.